- Remote, United States
- Remote
- Full-time · Staff
- $218K–$284K per year
- 5+ years
Senior Machine Learning Engineer for On-Device & Mobile AI, focused on optimizing state-of-the-art multi-modal models (transformers, diffusion networks, VLMs) to run fast, small, and reliably on mobile and constrained hardware within a browser-native runtime.
Compensation
Salary range : 218 400.00 USD - 283 900. 00 USD
Responsibilities
- Own the optimization pipeline for shipped models: model export, graph transformation, operator fusion, memory-layout planning, and hardware-specific tuning across NPU, mobile GPU, and desktop/laptop GPU.
- Apply quantization (INT4/INT8/FP16), weight sharing, structured/unstructured pruning, and knowledge distillation to meet latency, memory, and power budgets.
- Do low-level performance work: write and tune WebGPU compute shaders (WGSL) and native kernels (Metal, Vulkan/SPIR-V compute, CUDA), and profile using platform tools.
- Work with WebGPU-targeted inference runtimes (ONNX Runtime Web, Transformers.js, WebLLM, TensorFlow.js) alongside native options (CoreML, ONNX Runtime, TFLite, ExecuTorch).
- Build integration between the ML runtime and the game engine: real-time scheduling, memory pooling, zero-copy buffer sharing, and frame-budget management.
Requirements
- Not specified
- Nice to have: TypeScript/JavaScript
- Nice to have: NeRF
- Nice to have: 3DGS
- Nice to have: WebGPU deployment